Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3619 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5959. Min Range: -6.5959
Max Act: 6.5959. Min Act: -0.1700
Data Index: 7284544 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5959. Min Range: -6.5959
Max Act: 6.5959. Min Act: -0.1700
Data Index: 2084635 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5959. Min Range: -6.5959
Max Act: 6.5959. Min Act: -0.1700
Data Index: 3850739 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5959. Min Range: -6.5959
Max Act: 6.5959. Min Act: -0.1700
Data Index: 8422969 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5959. Min Range: -6.5959
Max Act: 6.5022. Min Act: -0.1700
Data Index: 1923250 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5959. Min Range: -6.5959
Max Act: 6.4397. Min Act: -0.1700
Data Index: 6426725 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5959. Min Range: -6.5959
Max Act: 6.4084. Min Act: -0.1700
Data Index: 2517906 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5959. Min Range: -6.5959
Max Act: 6.4084. Min Act: -0.1700
Data Index: 4810016 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5959. Min Range: -6.5959
Max Act: 6.4084. Min Act: -0.1700
Data Index: 5692222 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5959. Min Range: -6.5959
Max Act: 6.3772. Min Act: -0.1700
Data Index: 6546507 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5959. Min Range: -6.5959
Max Act: 6.2834. Min Act: -0.1700
Data Index: 5602865 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5959. Min Range: -6.5959
Max Act: 6.2522. Min Act: -0.1700
Data Index: 3191619 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5959. Min Range: -6.5959
Max Act: 6.2209. Min Act: -0.1700
Data Index: 1904806 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5959. Min Range: -6.5959
Max Act: 6.2209. Min Act: -0.1700
Data Index: 2069527 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5959. Min Range: -6.5959
Max Act: 6.2209. Min Act: -0.1700
Data Index: 2058140 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5959. Min Range: -6.5959
Max Act: 6.2209. Min Act: -0.1700
Data Index: 4338404 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5959. Min Range: -6.5959
Max Act: 6.2209. Min Act: -0.1700
Data Index: 919857 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5959. Min Range: -6.5959
Max Act: 6.2209. Min Act: -0.1700
Data Index: 1758656 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5959. Min Range: -6.5959
Max Act: 6.1897. Min Act: -0.1700
Data Index: 640832 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5959. Min Range: -6.5959
Max Act: 6.1897. Min Act: -0.1700
Data Index: 2997184 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #19